tuhinatripathi
commited on
Commit
•
c789d18
1
Parent(s):
adc10da
tuhinatripathi/gemma2b-lpr-5kdata-it
Browse files
README.md
CHANGED
@@ -6,7 +6,7 @@ tags:
|
|
6 |
- sft
|
7 |
- unsloth
|
8 |
- generated_from_trainer
|
9 |
-
base_model: unsloth/gemma-2b-bnb-4bit
|
10 |
model-index:
|
11 |
- name: gemma2b-5kdata
|
12 |
results: []
|
@@ -17,9 +17,9 @@ should probably proofread and complete it, then remove this comment. -->
|
|
17 |
|
18 |
# gemma2b-5kdata
|
19 |
|
20 |
-
This model is a fine-tuned version of [unsloth/gemma-2b-bnb-4bit](https://huggingface.co/unsloth/gemma-2b-bnb-4bit) on an unknown dataset.
|
21 |
It achieves the following results on the evaluation set:
|
22 |
-
- Loss: 0.
|
23 |
|
24 |
## Model description
|
25 |
|
@@ -54,7 +54,7 @@ The following hyperparameters were used during training:
|
|
54 |
|
55 |
| Training Loss | Epoch | Step | Validation Loss |
|
56 |
|:-------------:|:-----:|:----:|:---------------:|
|
57 |
-
| 1.
|
58 |
|
59 |
|
60 |
### Framework versions
|
|
|
6 |
- sft
|
7 |
- unsloth
|
8 |
- generated_from_trainer
|
9 |
+
base_model: unsloth/gemma-2b-it-bnb-4bit
|
10 |
model-index:
|
11 |
- name: gemma2b-5kdata
|
12 |
results: []
|
|
|
17 |
|
18 |
# gemma2b-5kdata
|
19 |
|
20 |
+
This model is a fine-tuned version of [unsloth/gemma-2b-it-bnb-4bit](https://huggingface.co/unsloth/gemma-2b-it-bnb-4bit) on an unknown dataset.
|
21 |
It achieves the following results on the evaluation set:
|
22 |
+
- Loss: 0.9939
|
23 |
|
24 |
## Model description
|
25 |
|
|
|
54 |
|
55 |
| Training Loss | Epoch | Step | Validation Loss |
|
56 |
|:-------------:|:-----:|:----:|:---------------:|
|
57 |
+
| 1.036 | 1.0 | 1250 | 0.9939 |
|
58 |
|
59 |
|
60 |
### Framework versions
|